rara-tools 0.7.17__tar.gz → 0.7.19__tar.gz

{rara_tools-0.7.17/rara_tools.egg-info → rara_tools-0.7.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rara-tools
-Version: 0.7.17
+Version: 0.7.19
 Summary: Tools to support Kata's work.
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10

rara_tools-0.7.19/VERSION

@@ -0,0 +1 @@
+0.7.19

{rara_tools-0.7.17 → rara_tools-0.7.19}/rara_tools/digar_schema_converter.py

@@ -77,7 +77,7 @@ class PageSchema:
             self.__schema = {
                 "@type": "CreativeWork",  # CONSTANT for pages
                 "@id": self.page_id,
-                "hasPart": []
+                "dcterms:hasPart": []
             }
             text_schemas = [
                 TextPageSchema(page).schema
@@ -91,7 +91,7 @@ class PageSchema:
             page_schemas = text_schemas + image_schemas
             page_schemas_with_ids = self._add_segment_ids(page_schemas)
 
-            self.__schema["hasPart"].extend(page_schemas_with_ids)
+            self.__schema["dcterms:hasPart"].extend(page_schemas_with_ids)
 
         return self.__schema
 
@@ -237,6 +237,7 @@ class DIGARSchemaConverter:
             generated_id: str,
             sierra_id: str = "",
             permalink: str = "",
+            hasPart_uri_prefix: str = None,
             generated_id_type: str = "CustomID",
             min_language_ratio: float = 0.2,
             convert_ratio: bool = False
@@ -253,6 +254,8 @@ class DIGARSchemaConverter:
             Document's corresponding Sierra ID.
         permalink: str
             Permanent link, where the document can be accessed.
+        hasPart_uri_prefix: str
+            Optional URI prefix for hasPart @ids.
         generated_id_type: str
             Method / type of generated ID (e.g. 'UUID')
         min_language_ratio: float
@@ -269,6 +272,7 @@ class DIGARSchemaConverter:
         self.__sierra_id: str = sierra_id
         self.__generated_id: str = generated_id
         self.__permalink: str = permalink.removesuffix("/")
+        self.__hasPart_uri_prefix = hasPart_uri_prefix.removesuffix("/") if hasPart_uri_prefix else None
         self.__generated_id_type: str = generated_id_type
         self.__texts: List[dict] = []
         self.__images: List[dict] = []
@@ -368,7 +372,6 @@ class DIGARSchemaConverter:
                 mapped[text["start_page"]]["texts"].append(text)
             for img in self.images:
                 mapped[img["page"]]["images"].append(img)
-            #print(mapped.items())
 
             self.__page_mappings = [
                 v for k, v in sorted(list(mapped.items()), key=lambda x: x[0])
@@ -378,13 +381,14 @@ class DIGARSchemaConverter:
     @property
     def dcterms_haspart(self) -> dict:
         if not self.__dcterms_haspart:
+            
             self.__dcterms_haspart = {
                 "dcterms:hasPart": [
                     PageSchema(
                         page_texts=page["texts"],
                         page_images=page["images"],
                         page_number=self._get_page_number(page),
-                        doc_id=self.doc_id
+                        doc_id=self.__hasPart_uri_prefix if self.__hasPart_uri_prefix else self.doc_id
                     ).schema
                     for page in self.page_mappings
                 ]

{rara_tools-0.7.17 → rara_tools-0.7.19/rara_tools.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rara-tools
-Version: 0.7.17
+Version: 0.7.19
 Summary: Tools to support Kata's work.
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10

{rara_tools-0.7.17 → rara_tools-0.7.19}/tests/test_digar_schema_converter.py

@@ -64,7 +64,7 @@ def test_digar_schema_id_generation():
 
     #If permalink is given, this should be used as base ID
     digar_schema = converter.digar_schema
-    first_segment_id = digar_schema["dcterms:hasPart"][0]["hasPart"][0]["@id"]
+    first_segment_id = digar_schema["dcterms:hasPart"][0]["dcterms:hasPart"][0]["@id"]
 
     assert first_segment_id.startswith(TEST_PERMALINK)
 
@@ -76,7 +76,7 @@ def test_digar_schema_id_generation():
 
     #If permalink is NOT given, Sierra ID should be used as base ID
     digar_schema = converter.digar_schema
-    first_segment_id = digar_schema["dcterms:hasPart"][0]["hasPart"][0]["@id"]
+    first_segment_id = digar_schema["dcterms:hasPart"][0]["dcterms:hasPart"][0]["@id"]
     assert first_segment_id.startswith(TEST_SIERRA_ID)
 
 
@@ -87,7 +87,7 @@ def test_digar_schema_id_generation():
 
     #If neiter permalink nor Sierra ID is given, generated ID should be used as base ID
     digar_schema = converter.digar_schema
-    first_segment_id = digar_schema["dcterms:hasPart"][0]["hasPart"][0]["@id"]
+    first_segment_id = digar_schema["dcterms:hasPart"][0]["dcterms:hasPart"][0]["@id"]
     assert first_segment_id.startswith(TEST_GENERATED_ID)
 
 

rara_tools-0.7.17/VERSION

@@ -1 +0,0 @@
-0.7.17